{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6FKI3MVNGBUAVHFC2SQN23HO5W","short_pith_number":"pith:6FKI3MVN","canonical_record":{"source":{"id":"2508.15096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6aa295f797c75336a3d0980416668363292f54630f3ae7143d76b900b7b98ee5","abstract_canon_sha256":"7cfa4424d1bb74c99a833bc03487d01df5e5f0c4bd82ec2f595598ede235c86c"},"schema_version":"1.0"},"canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","source":{"kind":"arxiv","id":"2508.15096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15096","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15096v1","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15096","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_12","alias_value":"6FKI3MVNGBUA","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_16","alias_value":"6FKI3MVNGBUAVHFC","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_8","alias_value":"6FKI3MVN","created_at":"2026-07-05T11:57:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6FKI3MVNGBUAVHFC2SQN23HO5W","target":"record","payload":{"canonical_record":{"source":{"id":"2508.15096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6aa295f797c75336a3d0980416668363292f54630f3ae7143d76b900b7b98ee5","abstract_canon_sha256":"7cfa4424d1bb74c99a833bc03487d01df5e5f0c4bd82ec2f595598ede235c86c"},"schema_version":"1.0"},"canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:06.406120Z","signature_b64":"8RzMmZwZcdWx9xb+2dTpREmIOiRJOCS3k768FIAW7GBY1TXtgXZBwASpvuqLDNcT0Y/jnF3kon+Oi2VpCaS4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","last_reissued_at":"2026-07-05T11:57:06.405622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:06.405622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.15096","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:57:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"il2VqxPkmYtQA+q/PdXcOLAB/7lGzLlEOAuM+IqkDUBd5CwFN20MmABJVGv+hj+DzLT1Ysxadd7H1WcKn5EtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:02:59.906079Z"},"content_sha256":"2343d461d3bc1049e7704a3f026f1f771e1921e0c7f6f3edc27576327fc9c1af","schema_version":"1.0","event_id":"sha256:2343d461d3bc1049e7704a3f026f1f771e1921e0c7f6f3edc27576327fc9c1af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6FKI3MVNGBUAVHFC2SQN23HO5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan Catanzaro, Mohammad Shoeybi, Mostofa Patwary, Rabeeh Karimi Mahabadi, Sanjeev Satheesh, Shrimai Prabhumoye","submitted_at":"2025-08-20T22:16:57Z","abstract_excerpt":"Pretraining large language models (LLMs) on high-quality, structured data such as mathematics and code substantially enhances reasoning capabilities. However, existing math-focused datasets built from Common Crawl suffer from degraded quality due to brittle extraction heuristics, lossy HTML-to-text conversion, and the failure to reliably preserve mathematical structure. In this work, we introduce Nemotron-CC-Math, a large-scale, high-quality mathematical corpus constructed from Common Crawl using a novel, domain-agnostic pipeline specifically designed for robust scientific text extraction.\n  U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15096","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.15096/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:57:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbJDOsEqqsoWtRUugPJBBFDQJzk364UvDVTmZh7lIBINhzH+tORHnb4MaAWgYtIXASC8DDh9k60mhNk+GhgGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:02:59.907003Z"},"content_sha256":"7f9903794c22cde039075bafa4ad48c751e037ac08b6172be4a6c83b7c83b57e","schema_version":"1.0","event_id":"sha256:7f9903794c22cde039075bafa4ad48c751e037ac08b6172be4a6c83b7c83b57e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FKI3MVNGBUAVHFC2SQN23HO5W/bundle.json","state_url":"https://pith.science/pith/6FKI3MVNGBUAVHFC2SQN23HO5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FKI3MVNGBUAVHFC2SQN23HO5W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T07:02:59Z","links":{"resolver":"https://pith.science/pith/6FKI3MVNGBUAVHFC2SQN23HO5W","bundle":"https://pith.science/pith/6FKI3MVNGBUAVHFC2SQN23HO5W/bundle.json","state":"https://pith.science/pith/6FKI3MVNGBUAVHFC2SQN23HO5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FKI3MVNGBUAVHFC2SQN23HO5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6FKI3MVNGBUAVHFC2SQN23HO5W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7cfa4424d1bb74c99a833bc03487d01df5e5f0c4bd82ec2f595598ede235c86c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","title_canon_sha256":"6aa295f797c75336a3d0980416668363292f54630f3ae7143d76b900b7b98ee5"},"schema_version":"1.0","source":{"id":"2508.15096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15096","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15096v1","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15096","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_12","alias_value":"6FKI3MVNGBUA","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_16","alias_value":"6FKI3MVNGBUAVHFC","created_at":"2026-07-05T11:57:06Z"},{"alias_kind":"pith_short_8","alias_value":"6FKI3MVN","created_at":"2026-07-05T11:57:06Z"}],"graph_snapshots":[{"event_id":"sha256:7f9903794c22cde039075bafa4ad48c751e037ac08b6172be4a6c83b7c83b57e","target":"graph","created_at":"2026-07-05T11:57:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.15096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining large language models (LLMs) on high-quality, structured data such as mathematics and code substantially enhances reasoning capabilities. However, existing math-focused datasets built from Common Crawl suffer from degraded quality due to brittle extraction heuristics, lossy HTML-to-text conversion, and the failure to reliably preserve mathematical structure. In this work, we introduce Nemotron-CC-Math, a large-scale, high-quality mathematical corpus constructed from Common Crawl using a novel, domain-agnostic pipeline specifically designed for robust scientific text extraction.\n  U","authors_text":"Bryan Catanzaro, Mohammad Shoeybi, Mostofa Patwary, Rabeeh Karimi Mahabadi, Sanjeev Satheesh, Shrimai Prabhumoye","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15096","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2343d461d3bc1049e7704a3f026f1f771e1921e0c7f6f3edc27576327fc9c1af","target":"record","created_at":"2026-07-05T11:57:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7cfa4424d1bb74c99a833bc03487d01df5e5f0c4bd82ec2f595598ede235c86c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T22:16:57Z","title_canon_sha256":"6aa295f797c75336a3d0980416668363292f54630f3ae7143d76b900b7b98ee5"},"schema_version":"1.0","source":{"id":"2508.15096","kind":"arxiv","version":1}},"canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1548db2ad30680a9ca2d4a0dd6ceeed806f05a517d84bda579f26e826c16bde","first_computed_at":"2026-07-05T11:57:06.405622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:06.405622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8RzMmZwZcdWx9xb+2dTpREmIOiRJOCS3k768FIAW7GBY1TXtgXZBwASpvuqLDNcT0Y/jnF3kon+Oi2VpCaS4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:06.406120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2343d461d3bc1049e7704a3f026f1f771e1921e0c7f6f3edc27576327fc9c1af","sha256:7f9903794c22cde039075bafa4ad48c751e037ac08b6172be4a6c83b7c83b57e"],"state_sha256":"7a929b517f1fb2d46f0b333b06b0a5d934444661b90c8521c654ebcf9325f9a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FfOjbSGILG/ESDsXmGtVyTesLPhY3X7yxa2O0MV/RDhfgG9gfs0xDGCqu6Ch9O5ixxGIzGJOu5Yzgwe1/n6FAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:02:59.916295Z","bundle_sha256":"405d88a97f820d308ba8226688d1ea52167cac2aff499130a9a8a52c87307a46"}}